Especialista em IA e Orquestração de Agentes

Team: IT

Location: Brazil

Commitment: Full-time

Workplace Type: remote

Accountabilities

• Develop applied AI solutions involving intelligent agents, LLM-based systems, and workflow orchestration.

• Build backend services and AI pipelines covering ingestion, vectorization, querying, retrieval, and response generation.

• Design and implement agent and workflow architectures using technologies such as LangChain, LangGraph, CrewAI, and n8n.

• Build and optimize RAG architectures, including chunking, embeddings, re-ranking, and context-window optimization.

• Integrate AI models and services through prompt engineering, tool calling, function calling, and specialized APIs.

• Connect AI solutions with external systems through REST APIs, webhooks, and structured databases such as SQL.

• Deploy, monitor, scale, and maintain AI solutions in Microsoft Azure environments, including Azure OpenAI, Functions, App Services, AI Search, and Storage/Data Lake.

• Apply software engineering best practices across architecture, development, testing, deployment, observability, and continuous improvement.

• Use Docker and CI/CD pipelines such as GitHub Actions to support reliable and repeatable software delivery.

• Take end-to-end ownership of AI solutions, from technical design through production implementation and ongoing optimization.

Requirements

• Proven experience developing applied AI solutions, particularly AI agents, LLM-based applications, and intelligent workflow orchestration.

• Strong proficiency in Python or Node.js for backend development and AI pipeline implementation.

• Hands-on experience with agent and orchestration frameworks such as LangChain, LangGraph, CrewAI, and n8n.

• Solid knowledge of RAG architectures, including chunking, embeddings, re-ranking, and context-window optimization.

• Experience working with vector databases or search technologies such as Pinecone, Weaviate, Chroma, or Azure AI Search.

• Familiarity with AI providers and models including OpenAI, Azure OpenAI, and open-source models such as LLaMA and Mistral through Ollama.

• Advanced prompt engineering skills and practical experience with tool calling and function calling.

• Experience integrating systems through REST APIs and webhooks, as well as working with structured databases such as SQL.

• Experience deploying and operating AI solutions in Microsoft Azure, including cloud monitoring, observability, and scalability.

• Knowledge of Docker and CI/CD practices, particularly with GitHub Actions.

• Strong software architecture knowledge and the ability to work independently across the complete development lifecycle.

• Ability to approach complex technical challenges analytically and translate AI capabilities into reliable, scalable solutions.

• Strong collaboration, communication, ownership, and problem-solving skills.

Benefits

• 100% remote work model, enabling professionals to work from anywhere in Brazil.

• Legal-person (PJ) engagement model.

• Opportunity to work on applied Artificial Intelligence, LLMs, intelligent agents, RAG, and workflow orchestration.

• Exposure to modern cloud technologies and Microsoft Azure AI services.

• Collaborative and technology-focused environment with opportunities to work on innovative digital solutions.

• Culture focused on collaboration, respect, diversity, equity, and inclusion.

• Opportunity to develop expertise across the full AI engineering lifecycle, from architecture and development to deployment and observability.

• Professional environment that values technological innovation and continuous development.